Training in progress, step 6210, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1b7f06475956bfbde9322f3b5e942fe7645bda14051ff5b1ef4c51902bfce67
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6acd72d867070849dd69b824239e5142694e7fb6a32dd0e8f6bd35c64c735cac
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75077102a30b80de4c332d54b957dd3ccf62298368a0d34cb42f9327de1d3ae5
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 47.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -11168,6 +11168,24 @@
|
|
| 11168 |
"mean_token_accuracy": 0.6648684412240982,
|
| 11169 |
"num_tokens": 22613662.0,
|
| 11170 |
"step": 6200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11171 |
}
|
| 11172 |
],
|
| 11173 |
"logging_steps": 5,
|
|
@@ -11187,7 +11205,7 @@
|
|
| 11187 |
"attributes": {}
|
| 11188 |
}
|
| 11189 |
},
|
| 11190 |
-
"total_flos": 1.
|
| 11191 |
"train_batch_size": 4,
|
| 11192 |
"trial_name": null,
|
| 11193 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11168 |
"mean_token_accuracy": 0.6648684412240982,
|
| 11169 |
"num_tokens": 22613662.0,
|
| 11170 |
"step": 6200
|
| 11171 |
+
},
|
| 11172 |
+
{
|
| 11173 |
+
"epoch": 47.73076923076923,
|
| 11174 |
+
"grad_norm": 0.0,
|
| 11175 |
+
"learning_rate": 1.898e-05,
|
| 11176 |
+
"loss": 1.7837,
|
| 11177 |
+
"mean_token_accuracy": 0.6461777001619339,
|
| 11178 |
+
"num_tokens": 22631498.0,
|
| 11179 |
+
"step": 6205
|
| 11180 |
+
},
|
| 11181 |
+
{
|
| 11182 |
+
"epoch": 47.76923076923077,
|
| 11183 |
+
"grad_norm": 0.0,
|
| 11184 |
+
"learning_rate": 1.8955e-05,
|
| 11185 |
+
"loss": 1.8125,
|
| 11186 |
+
"mean_token_accuracy": 0.6402515649795533,
|
| 11187 |
+
"num_tokens": 22648506.0,
|
| 11188 |
+
"step": 6210
|
| 11189 |
}
|
| 11190 |
],
|
| 11191 |
"logging_steps": 5,
|
|
|
|
| 11205 |
"attributes": {}
|
| 11206 |
}
|
| 11207 |
},
|
| 11208 |
+
"total_flos": 1.1480657955574579e+18,
|
| 11209 |
"train_batch_size": 4,
|
| 11210 |
"trial_name": null,
|
| 11211 |
"trial_params": null
|